© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 340
    Prev
    Next
    INDEX
    Explanations

    code components

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on programming identifiers for classes, interfaces, methods, or listeners (e.g. class names and API callbacks).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     procha
    -1.12
    Արտաքին
    -1.09
    дка
    -1.08
    涐
    -1.08
    batterie
    -1.04
    tadır
    -1.03
    衚
    -1.03
    tront
    -1.02
    龕
    -1.02
    🤛
    -1.02
    POSITIVE LOGITS
    i
    1.20
     управление
    1.05
     flyers
    1.00
    寓意
    0.99
    g
    0.98
     insbesondere
    0.97
    美子
    0.95
    +}$
    0.94
    𝘦
    0.94
    ,”
    0.92
    Activations Density 0.001%

    No Known Activations